def testMoreElaborate(seed):
# Confirm that HMC still works in the presence of brush. Do not,
# however, mess with the possibility that the principal nodes that
# HMC operates over may themselves be in the brush.
ripl = get_ripl(seed=seed)
ripl.assume("x", "(tag (quote param) 0 (uniform_continuous -10 10))")
ripl.assume("y",
"(tag (quote param) 1 (uniform_continuous -10 10))",
label="pid")
ripl.assume("xout", """
(if (< x 0)
(normal x 1)
(normal x 2))""")
ripl.assume(
"out",
"(multivariate_normal (array xout y) (matrix (list (list 1 0.5) (list 0.5 1))))"
)
# Note: Can't observe coordinatewise because observe is not flexible
# enough. For this to work we would need observations of splits.
# ripl.observe("(lookup out 0)", 0)
# ripl.observe("(lookup out 1)", 0)
# Can't observe through the ripl literally because the string
# substitution (!) is not flexible enough.
# ripl.observe("out", [0, 0])
ripl.observe("out", val.list([val.real(0), val.real(0)]))
preds_mh = collectSamples(ripl,
"pid",
infer="(resimulation_mh default one 10)")
ripl.sivm.core_sivm.engine.reinit_inference_problem()
preds_hmc = collectSamples(ripl, "pid", infer="(hmc 'param all 0.1 20 10)")
return reportSameContinuous(preds_mh, preds_hmc)
def compareSampleDicts(dicts_hists,labels,plot=False):
'''Input: dicts_hists :: ({exp:values}) | (History)
where the first Series in History is used as values. History's are
converted to dicts.'''
if not isinstance(dicts_hists[0],dict):
dicts = [historyNameToValues(h,seriesInd=0) for h in dicts_hists]
else:
dicts = dicts_hists
dicts = map(filterScalar,dicts) # could skip for Analytics
stats = (np.mean,np.median,np.std,len) # FIXME stderr
stats_dict = {}
print 'compareSampleDicts: %s vs. %s \n'%(labels[0],labels[1])
for exp in dicts[0].keys():
stats_dict[exp] = []
for dict_i,label_i in zip(dicts,labels):
samples=dict_i[exp]
s_stats = tuple([s(samples) for s in stats])
stats_dict[exp].append(s_stats)
print '\nDict: %s. Exp: %s'%(label_i,exp)
print 'Mean, median, std, N = %.3f %.3f %.3f %i'%s_stats
testResult=reportSameContinuous(dicts[0][exp],dicts[1][exp])
print 'KS SameContinuous:', ' '.join(testResult.report.split('\n')[-2:])
stats_dict[exp].append( testResult )
fig = qqPlotAll(dicts,labels) if plot else None
return stats_dict,fig
def testForceBrush5(seed):
ripl = get_ripl(seed=seed)
ripl.assume("x", "(normal 0 1)", label="pid")
ripl.assume("y", "(if (< x 0) (normal x 1) (normal (+ x 10) 1))")
ripl.observe("y", 8)
preds_mh = collectSamples(ripl, "pid", infer="(mh default one 10)")
ripl.sivm.core_sivm.engine.reinit_inference_problem()
preds_hmc = collectSamples(ripl,
"pid",
infer="(hmc default one 0.1 20 10)")
return reportSameContinuous(preds_mh, preds_hmc)
def testRollingResample():
ripl = get_ripl()
ripl.assume("a", "(normal 10.0 1.0)", label="pid")
ripl.observe("(normal a 1.0)", 14.0)
flat_resample = "(do (resample 5) (likelihood_weight) (resample 1))"
predictions1 = collectSamples(ripl, "pid", infer=flat_resample)
rolling_resample = "(repeat 5 (do add_particle (resample 1)))"
predictions2 = collectSamples(ripl, "pid", infer=rolling_resample)
return reportSameContinuous(predictions1, predictions2)
def testAAAHyperInference(seed):
def try_at_five(maker):
r = get_ripl(seed=seed)
r.assume("mu", "(normal 0 1)")
r.assume("obs", "(%s mu 1 1 1)" % maker)
r.observe("(obs)", 5)
infer = "(mh default all %d)" % default_num_transitions_per_sample()
return collectSamples(r,
"mu",
infer=infer,
num_samples=default_num_samples(2))
collapsed = try_at_five("make_nig_normal")
uncollapsed = try_at_five("make_uc_nig_normal")
return reportSameContinuous(collapsed, uncollapsed)
def testTwoSampleKS(seed):
rng = np.random.RandomState(seed)
data1 = rng.normal(size=100, loc=0., scale=1)
data2 = rng.normal(size=100, loc=0., scale=1)
return reportSameContinuous(data1, data2)
